Authors:
Mattias Billast
1
;
Kevin Mets
2
;
Tom De Schepper
1
;
José Oramas
1
and
Steven Latré
1
Affiliations:
1
University of Antwerp - imec, IDLab, Department of Computer Science, Sint-Pietersvliet 7, 2000 Antwerp, Belgium
;
2
University of Antwerp - imec, IDLab, Faculty of Applied Engineering, Sint-Pietersvliet 7, 2000 Antwerp, Belgium
Keyword(s):
Motion Prediction, Graph Neural Network, IKEA-ASM.
Abstract:
Motion prediction of the human pose estimates future poses based on the preceding poses. It is a stepping stone toward industrial applications, like human-robot interactions and ergonomy indicators. The goal is to minimize the error in predicted joint positions on the IKEA-ASM dataset which resembles assembly use cases with a high diversity of execution and background of the same action class. In this paper, we use the STS-GCN model to tackle 2D motion prediction and make various alterations to improve the performance of the model. First, we pre-processed the training dataset through filtering to remove outliers and inconsistencies to boost performance by 31%. Secondly, we added object gaze information to give more context to the body motion of the subject, which lowers the error (MPJPE) to 10.1618 compared to 18.3462 without object gaze information. The increased performance indicates that there is a correlation between the object gaze and body motion. Lastly, the over-smoothing of
the Graph Convolutional Network embeddings is decreased by limiting the number of layers, providing richer joint embeddings.
(More)